CoFi-Dec：通过粗到细的生成反馈在大视觉-语言模型中实现抗幻觉解码
CoFi-Dec: Hallucination-Resistant Decoding via Coarse-to-Fine Generative Feedback in Large Vision-Language Models
AI总结：
CoFi-Dec通过粗到细的生成反馈机制，在大视觉-语言模型中减少幻觉，提升解码的鲁棒性和准确性。
摘要：
大视觉-语言模型（LVLMs）在多模态理解和生成方面取得了显著进展。然而，它们仍然倾向于生成与视觉输入不一致的幻觉内容，这限制了它们在现实世界中的可靠性。我们提出了CoFi-Dec，一种无需训练的解码框架，通过整合生成性自我反馈与粗到细的视觉条件化来减轻幻觉。受人类视觉过程从全局场景感知到细节检查的启发，CoFi-Dec首先生成两个受原始图像粗粒度和细粒度视图条件化的中间文本响应。这些响应随后通过文本到图像模型转换为合成图像，形成多级视觉假设，丰富了 grounding cues。为了统一这些多重视觉条件的预测，我们引入了基于Wasserstein的融合机制，将它们的预测分布对齐到几何上一致的解码轨迹。这种原理性的融合协调了高层语义一致性和细粒度视觉定位，导致更加稳健和忠实的输出。在六个专注于幻觉的基准测试中进行了广泛的实验，结果表明CoFi-Dec显著减少了实体级和语义级的幻觉，优于现有的解码策略。该框架模型无关，不需要额外训练，并可以无缝应用于广泛的大视觉-语言模型。实现可在https://github.com/AI-Researcher-Team/CoFi-Dec上获得。
英文摘要：
Large Vision-Language Models (LVLMs) have achieved impressive progress in multi-modal understanding and generation. However, they still tend to produce hallucinated content that is inconsistent with the visual input, which limits their reliability in real-world applications. We propose \textbf{CoFi-Dec}, a training-free decoding framework that mitigates hallucinations by integrating generative self-feedback with coarse-to-fine visual conditioning. Inspired by the human visual process from global scene perception to detailed inspection, CoFi-Dec first generates two intermediate textual responses conditioned on coarse- and fine-grained views of the original image. These responses are then transformed into synthetic images using a text-to-image model, forming multi-level visual hypotheses that enrich grounding cues. To unify the predictions from these multiple visual conditions, we introduce a Wasserstein-based fusion mechanism that aligns their predictive distributions into a geometrically consistent decoding trajectory. This principled fusion reconciles high-level semantic consistency with fine-grained visual grounding, leading to more robust and faithful outputs. Extensive experiments on six hallucination-focused benchmarks show that CoFi-Dec substantially reduces both entity-level and semantic-level hallucinations, outperforming existing decoding strategies. The framework is model-agnostic, requires no additional training, and can be seamlessly applied to a wide range of LVLMs. The implementation is available at https://github.com/AI-Researcher-Team/CoFi-Dec.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
